INDEX

Explanations

names of people and their appearances or mentions in text

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ricular

-0.87

shaw

-0.82

dp

-0.82

rient

-0.79

ribution

-0.79

Ã§a

-0.78

ests

-0.77

cise

-0.75

pping

-0.73

iding

-0.73

POSITIVE LOGITS

Pause

0.79

iary

0.79

 prominently

0.76

ãĤ¤ãĥĪ

0.72

 contradictions

0.72

 poised

0.71

DragonMagazine

0.71

ively

0.70

Crash

0.68

 Minion

0.68

Activations Density 8.549%

names of people and their appearances or mentions in text

No Comments

No Known Activations